Timezone: »

Iterative Teaching by Label Synthesis
Weiyang Liu · Zhen Liu · Hanchen Wang · Liam Paull · Bernhard Schölkopf · Adrian Weller

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @

In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner. In contrast to previous methods that have to scan over the entire pool and select teaching examples from it in each iteration, we propose a label synthesis teaching framework where the teacher randomly selects input teaching examples (e.g., images) and then synthesizes suitable outputs (e.g., labels) for them. We show that this framework can avoid costly example selection while still provably achieving exponential teachability. We propose multiple novel teaching algorithms in this framework. Finally, we empirically demonstrate the value of our framework.

Author Information

Weiyang Liu (University of Cambridge)
Zhen Liu (University of Montreal, MILA)
Hanchen Wang (University of Cambridge)

Hey, I am a 3rd Year PhD Student in Machine Learning at Cambridge, where I work with Joan Lasenby and Adrian Weller on Geometric Deep Learning (3D, Graph). Please check my website for my recent updates :)

Liam Paull (Université de Montréal)
Bernhard Schölkopf (MPI for Intelligent Systems, Tübingen)
Adrian Weller (University of Cambridge )

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors